Detecting the Saliency of Remote Sensing Images Based on Sparse Representation of Contrast-weighted Atoms

Object detection is an important task in remote sensing (RS) image analysis. To reduce the computational complexity of redundant information and improve the efficiency of image processing, visual saliency models are gradually being applied in this field. In this paper, a novel saliency detection method is proposed by exploring the sparse representation (SR) of, based on learning, contrast-weighted atoms (LCWA). Specifically, this paper uses the proposed LCWA atom learning formula on positive and negative samples to construct a saliency dictionary, and on nonsaliency atoms to construct a discriminant dictionary. An online discriminant dictionary learning algorithm is proposed to solve the atom learning formula. Then, we measure saliency by combining the coefficients of SR and reconstruction errors. Furthermore, under the proposed joint saliency measure, a variety of salient maps are generated by the discriminant dictionary. Finally, a fusion method based on global gradient optimisation is proposed to integrate multiple salient maps. Experimental results show that the proposed method significantly outperforms current state-of-the-art methods under six evaluation measures.